19IT111_19IT116_Credit Card Fruad Detection

on

 

Credit Card Fraud Detection Using Machine Learning


Today the banking sector offers its clients many different financial services such as ATM cards, Internet banking, Debit card, and Credit card, which allows attracting a large number of new customers. E-commerce and many other online sites have increased the online payment modes, increasing the risk for online frauds. 

'Fraud’ in credit  card  transactions  is  unauthorized  and unwanted  usage  of  an  account  by  someone  other  than  the owner of that account. Necessary prevention measures can be taken to stop this abuse and the behavior of such fraudulent practices can be studied to minimize it and protect against similar occurrences in the future.




We have design a machine learning algorithm which will help detecting frauds. We collected over 2 million of data with around 28 different features including some confidential info., amount of transaction and time of transaction.




This is a very important aspect to consider in order to live peacefully by a normal person, and also the frauds who commit such thing learn a lesson and get handcuffed!





WHAT IS MACHINE LEARNING?


Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

We used python to implement our algorithm as:
  • It has a huge number of libraries and frameworks like NumPy, SciKit, SciPy… . 
  • Python code is concise and readable. Development of application is faster as it has easy syntax. 
  • Python is an open-source programming language, hence, has large online support available.
  • Performance of python is as fast as C language.
As the reason behind selection was that it supports many libraries, so here are some which we used :

Seaborn: used for making statistical graphics.
SciPy: It provides more utility functions for optimization, stats and signal processing.
Sklearn: features various algorithms like support vector machine, random forests, and k – neighbors
NumPy: provides fast mathematical computation on arrays and matrices.
Matplotlib: visualization library in Python for 2D plots of arrays.
Pandas: Software library used for data manipulation and analysis.

WHAT IS FRUAD DETECTION?


Fraud Detection with Machine Learning is a process of data investigation by a Data Science team and the development of a model that will provide the best results in revealing and preventing fraudulent transactions.





Some of  the currently  used approaches  to detection of  such fraud are:

  • Artificial Neural Network 
  • Fuzzy Logic 
  • Genetic Algorithm 
  • Logistic Regression  
  • Decision tree 
  • Support Vector Machines 
  • Bayesian Networks 
  • Hidden Markov Model 
  • K-Nearest Neighbor

Here are the various results we got till now from our algorithm:





THE CORRELATION:




FINAL CONCLUSION OR RESULT:










PROJECT CREDITS:

19IT111 (SHREYAS PATEL)
19IT116 (VRUND PATEL)

Comments

Post a Comment